Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A computer-implemented method comprising: establishing an elastic network bandwidth allocation level that a network service provider of an elastic network is to provide to a data center for an application for transfer of data between the application and the elastic network, the application hosted at the data center, wherein the network service provider is configured to dynamically modify the elastic network bandwidth allocation level provided by the network service provider to the data center based on control by a component to change an amount of elastic network bandwidth being provided by the network service provider to the data center; dynamically configuring, for the application, elastic network bandwidth allocation to the data center from the network service provider in accordance with the established elastic network bandwidth allocation level; and allocating storage resources of the data center for the application and processing resources of the data center for the application, the allocating being based on the established elastic network bandwidth allocation level and providing storage resources and processing resources to operate at a level commensurate with the established elastic network bandwidth allocation level.
This invention relates to dynamically managing network bandwidth and data center resources for applications hosted in a data center. The problem addressed is the inefficient allocation of network bandwidth and computing resources, which can lead to performance bottlenecks or underutilization. The solution involves a computer-implemented method that dynamically adjusts network bandwidth allocation and data center resources based on application needs. The method establishes an elastic network bandwidth allocation level that a network service provider delivers to a data center for an application. The network service provider can dynamically modify this bandwidth allocation based on control signals from a management component. The method then configures the elastic network bandwidth for the application according to the established allocation level. Additionally, it allocates storage and processing resources in the data center to match the bandwidth level, ensuring that storage and processing resources operate at a level commensurate with the network bandwidth. This coordination prevents resource mismatches, optimizing performance and cost efficiency. The dynamic adjustments allow the system to scale resources up or down as needed, improving flexibility and responsiveness to changing application demands.
2. The method of claim 1 , wherein the establishing comprises establishing the elastic network bandwidth allocation level based on anticipated network demand by the application.
A system and method for dynamically adjusting network bandwidth allocation in a computing environment to optimize performance for applications with varying network demands. The invention addresses the challenge of inefficient bandwidth utilization in networks where static allocation leads to either underutilization or congestion, particularly in environments with fluctuating application requirements. The method involves monitoring network traffic patterns and application behavior to predict future demand. Based on this analysis, the system dynamically adjusts the allocated bandwidth to ensure sufficient resources are available for critical applications while avoiding unnecessary allocation to idle or low-priority tasks. The adjustment process considers factors such as historical usage, application priority, and real-time network conditions to determine the optimal bandwidth level. A key aspect of the invention is the ability to establish an elastic network bandwidth allocation level, which automatically scales up or down in response to anticipated demand. This ensures that applications receive the necessary bandwidth to maintain performance without wasting resources. The system may also incorporate machine learning or predictive algorithms to improve accuracy in forecasting demand and adjusting allocations accordingly. By dynamically allocating bandwidth, the invention improves network efficiency, reduces latency for high-priority applications, and prevents congestion during peak usage periods. This approach is particularly useful in cloud computing, data centers, and enterprise networks where multiple applications compete for limited bandwidth resources.
3. The method of claim 2 , wherein the anticipated network demand is based on one or more of: a usage input or historical analysis.
A system and method for predicting network demand to optimize resource allocation in communication networks. The invention addresses the challenge of efficiently managing network resources by accurately forecasting demand to prevent congestion and ensure quality of service. The method involves analyzing historical network usage data and real-time usage inputs to generate an anticipated network demand. This demand prediction is used to dynamically adjust network configurations, such as bandwidth allocation, routing paths, or server load distribution, to meet expected traffic patterns. The system may also incorporate machine learning algorithms to refine predictions over time by correlating historical trends with current usage inputs. By leveraging both historical analysis and real-time data, the method ensures proactive resource management, reducing latency and improving overall network performance. The invention is applicable to various network types, including wireless, wired, and cloud-based systems, where demand fluctuations can significantly impact service quality. The solution enhances scalability and reliability by aligning resource allocation with anticipated usage, minimizing downtime and optimizing cost efficiency.
4. The method of claim 1 , wherein the establishing is based on one or more of: storage quality of service, network capacity efficiency, or compute demand.
A system and method optimize resource allocation in a distributed computing environment by dynamically establishing connections between storage nodes and compute nodes. The method evaluates multiple factors to determine optimal connections, including storage quality of service (QoS) metrics such as latency, throughput, and reliability, network capacity efficiency to minimize bandwidth usage and reduce congestion, and compute demand to balance workload distribution. By analyzing these factors, the system ensures efficient data access, minimizes network overhead, and aligns compute resources with workload requirements. The method may involve monitoring real-time performance metrics, predicting future demand, and dynamically adjusting connections to maintain optimal performance. This approach improves overall system efficiency, reduces operational costs, and enhances scalability in distributed computing environments.
5. The method of claim 1 , wherein the storage resources comprise storage input/output ports of a storage unit of the data center.
A method for managing storage resources in a data center involves optimizing the allocation and utilization of storage input/output (I/O) ports within a storage unit. The storage unit is part of a larger data center infrastructure, where efficient resource management is critical to maintaining performance and reliability. The method addresses the challenge of dynamically adjusting storage I/O port usage to accommodate varying workload demands, ensuring that data access remains efficient and bottlenecks are minimized. The storage unit includes multiple I/O ports that facilitate data transfer between storage devices and other components in the data center. The method dynamically allocates these ports based on real-time workload requirements, prioritizing high-demand tasks while balancing the load across available ports. This dynamic allocation helps prevent overutilization of specific ports, which could lead to performance degradation or system failures. Additionally, the method may involve monitoring the performance metrics of the storage I/O ports, such as latency, throughput, and error rates, to make informed allocation decisions. By continuously adjusting port assignments, the system ensures that storage resources are used optimally, reducing downtime and improving overall data center efficiency. The approach is particularly useful in environments with fluctuating workloads, where static port assignments would be inefficient.
6. The method of claim 5 , further comprising tracking storage input/output port capacity.
A system and method for monitoring and managing storage input/output (I/O) port capacity in a data storage environment. The technology addresses the challenge of efficiently allocating and optimizing I/O port resources to prevent bottlenecks and ensure high-performance data access. The method involves continuously monitoring the capacity and utilization of storage I/O ports, which are critical interfaces between storage devices and computing systems. By tracking port capacity, the system can detect potential overload conditions, dynamically adjust resource allocation, and maintain optimal performance levels. This includes measuring data transfer rates, latency, and other performance metrics to assess port efficiency. The method may also integrate with load balancing algorithms to distribute I/O operations evenly across available ports, reducing congestion and improving overall system responsiveness. Additionally, predictive analytics can be applied to anticipate future demand and proactively adjust configurations. The solution is particularly useful in high-demand environments such as data centers, cloud storage systems, and enterprise networks where I/O performance directly impacts operational efficiency. By ensuring that storage I/O ports operate within their optimal capacity, the system enhances reliability, reduces downtime, and supports scalable data management.
7. The method of claim 1 , wherein the storage resources comprise storage input/output operations per second of a storage unit of the data center.
A method for managing storage resources in a data center involves monitoring and optimizing storage input/output operations per second (IOPS) of storage units. The storage resources are allocated based on performance metrics, such as IOPS, to ensure efficient data handling and reduce latency. The method dynamically adjusts resource allocation in response to workload demands, balancing performance and cost. By tracking IOPS, the system identifies bottlenecks and reallocates storage capacity to maintain optimal performance. This approach prevents over-provisioning and underutilization, improving overall data center efficiency. The method integrates with existing storage management systems to provide real-time adjustments, ensuring seamless operation without manual intervention. The solution is particularly useful in high-demand environments where storage performance directly impacts application responsiveness. By focusing on IOPS as a key metric, the method ensures that storage resources are used effectively, reducing costs and enhancing reliability. The system may also include predictive analytics to anticipate future workload changes and preemptively adjust resource allocation. This proactive approach minimizes disruptions and maintains consistent performance levels. The method is applicable to various storage technologies, including solid-state drives (SSDs), hard disk drives (HDDs), and hybrid storage systems. The dynamic allocation of IOPS-based storage resources ensures that data center operations remain efficient and scalable.
8. The method of claim 1 , wherein the processing resources comprise virtualized storage area network processing power of a storage area network component.
A method for optimizing storage area network (SAN) performance involves utilizing virtualized processing resources from a SAN component to enhance data management. The SAN component provides dedicated processing power to handle storage operations, reducing latency and improving efficiency. This virtualized processing power can be dynamically allocated based on workload demands, ensuring optimal resource utilization. The method includes monitoring storage performance metrics, such as input/output operations per second (IOPS) and latency, to identify bottlenecks. When performance degradation is detected, the virtualized processing resources are automatically adjusted to mitigate the issue. The SAN component may include hardware accelerators or specialized processors designed for storage tasks, such as deduplication, compression, or encryption. By offloading these tasks to the virtualized processing resources, the overall system performance is improved, and the computational load on host systems is reduced. The method ensures that storage operations are executed efficiently, minimizing delays and maximizing throughput in enterprise storage environments.
9. The method of claim 1 , wherein the processing resources comprise virtualized processor power for one or more application servers.
This invention relates to resource management in computing systems, specifically optimizing processing resources for application servers. The problem addressed is inefficient allocation of computational power, leading to performance bottlenecks or underutilization in server environments. The solution involves dynamically allocating virtualized processor power to one or more application servers based on demand. Virtualization allows multiple servers to share physical hardware resources while maintaining isolation, improving scalability and cost-efficiency. The system monitors workloads and adjusts processor allocation in real-time to ensure optimal performance. This approach prevents over-provisioning or under-provisioning of resources, enhancing system responsiveness and reducing operational costs. The method may also include load balancing, where processing tasks are distributed across available virtualized resources to prevent any single server from becoming a bottleneck. By leveraging virtualization, the system can scale resources up or down as needed, adapting to fluctuating workloads without requiring physical hardware changes. This dynamic allocation ensures that application servers receive the necessary computational power to handle their tasks efficiently while minimizing idle resources. The invention is particularly useful in cloud computing and data center environments where resource optimization is critical.
10. The method of claim 1 , wherein the application comprises a multi-tenant application servicing a plurality of different customers, wherein the establishing, dynamically configuring, and allocating the storage resources and processing resources are tailored to a first customer of the plurality of different customers, and wherein the method repeats the establishing, dynamically configuring, and allocating storage resources and processing resources tailored for each additional customer of the plurality of different customers.
A multi-tenant application system dynamically allocates storage and processing resources to different customers. The system services multiple distinct customers, each with unique requirements, and tailors resource allocation specifically for each customer. This involves establishing, dynamically configuring, and allocating storage and processing resources based on the needs of a first customer, then repeating the process for each additional customer. The dynamic configuration ensures that resources are optimized for each customer's workload, improving efficiency and performance. The system avoids static resource allocation, instead adapting to varying demands across different tenants. This approach enhances scalability and cost-effectiveness by ensuring resources are used efficiently without over-provisioning. The method applies to cloud-based or distributed computing environments where multiple customers share infrastructure while maintaining isolated and customized resource management. The solution addresses challenges in multi-tenant systems where resource allocation must balance performance, cost, and isolation for diverse customer workloads.
11. A computer program product comprising: a computer readable storage medium readable by a processor and storing instructions for execution by the processor for performing a method comprising: establishing an elastic network bandwidth allocation level that a network service provider of an elastic network is to provide to a data center for an application for transfer of data between the application and the elastic network, the application hosted at the data center, wherein the network service provider is configured to dynamically modify the elastic network bandwidth allocation level provided by the network service provider to the data center based on control by a component to change an amount of elastic network bandwidth being provided by the network service provider to the data center; dynamically configuring for the application, elastic network bandwidth allocation to the data center from the network service provider in accordance with the established elastic network bandwidth allocation level; and allocating storage resources of the data center for the application and processing resources of the data center for the application, the allocating being based on the established elastic network bandwidth allocation level and providing storage resources and processing resources to operate at a level commensurate with the established elastic network bandwidth allocation level.
This invention relates to dynamic resource allocation in data centers for applications utilizing elastic network bandwidth. The problem addressed is the inefficient use of network, storage, and processing resources when bandwidth allocation is static, leading to underutilization or over-provisioning. The solution involves a system where a network service provider dynamically adjusts the bandwidth allocation to a data center based on application needs, while the data center automatically scales storage and processing resources to match the allocated bandwidth level. The elastic network bandwidth allocation level is initially established for an application hosted in the data center, determining the data transfer capacity between the application and the elastic network. A control component allows the network service provider to modify this allocation dynamically. The data center then configures the bandwidth allocation accordingly and allocates storage and processing resources proportionally to the bandwidth level, ensuring all resources operate at a balanced and efficient level. This coordinated scaling prevents resource waste and ensures optimal performance for the application.
12. The computer program product of claim 11 , wherein the establishing comprises establishing the elastic network bandwidth allocation level based on anticipated network demand by the application.
A system and method for dynamically allocating elastic network bandwidth in a computing environment addresses the challenge of efficiently managing network resources to meet varying application demands. The invention provides a computer program product that adjusts network bandwidth allocation in response to anticipated application needs, optimizing resource utilization and performance. The system monitors application behavior and network conditions to predict future demand, then dynamically allocates bandwidth accordingly. This includes adjusting bandwidth levels based on factors such as application workload patterns, historical usage data, and real-time network performance metrics. By proactively scaling bandwidth up or down, the system ensures that applications receive sufficient resources during peak demand periods while avoiding over-provisioning during low-activity phases. The elastic allocation mechanism may also incorporate policies or rules to prioritize certain applications or services, ensuring critical operations receive adequate bandwidth. The solution improves network efficiency, reduces costs associated with over-provisioning, and enhances overall system performance by aligning bandwidth allocation with actual application requirements.
13. The computer program product of claim 11 , wherein the storage resources comprise at least one selected from the group consisting of: storage input/output ports of a storage unit of the data center, and storage input/output operations per second of a storage unit of the data center.
This invention relates to optimizing storage resource allocation in data centers. The problem addressed is inefficient utilization of storage resources, which can lead to performance bottlenecks and wasted capacity. The invention provides a computer program product that monitors and manages storage resources in a data center to improve efficiency. The storage resources being managed include storage input/output (I/O) ports and storage I/O operations per second (IOPS) of storage units within the data center. The program product dynamically allocates these resources based on real-time demand, ensuring that storage units are used optimally. By tracking I/O port availability and IOPS performance, the system can redistribute workloads to prevent overutilization of any single storage unit, thereby enhancing overall data center performance. The invention also includes mechanisms to predict future storage resource needs based on historical usage patterns and current workload trends. This predictive capability allows for proactive resource allocation, reducing the likelihood of performance degradation during peak usage periods. Additionally, the system can generate alerts when storage resources are approaching capacity limits, enabling administrators to take corrective action before issues arise. By focusing on key storage metrics such as I/O ports and IOPS, the invention ensures that storage resources are allocated in a way that maximizes efficiency and minimizes downtime. This approach is particularly valuable in large-scale data centers where storage demands can fluctuate significantly.
14. The computer program product of claim 11 , wherein the processing resources comprise at least one selected from the group consisting of: virtualized storage area network processing power of a storage area network component or virtualized processor power for one or more application servers.
This invention relates to a computer program product for managing processing resources in a data center environment, particularly addressing the challenge of efficiently allocating and utilizing computing resources to optimize performance and cost. The system dynamically allocates processing power from virtualized storage area network (SAN) components or virtualized processors for application servers, ensuring that resources are distributed based on demand. The virtualized SAN processing power allows storage-related tasks to be handled more efficiently, while virtualized processor power for application servers enables flexible scaling of computational resources. This approach improves resource utilization, reduces overhead, and enhances overall system performance by dynamically adjusting to workload requirements. The invention is particularly useful in cloud computing and enterprise data center environments where resource allocation must be both scalable and cost-effective. By leveraging virtualization, the system ensures that processing power is allocated where it is needed most, minimizing idle resources and maximizing efficiency. The solution is designed to integrate seamlessly with existing infrastructure, providing a flexible and adaptive resource management framework.
15. The computer program product of claim 11 , wherein the application comprises a multi-tenant application servicing a plurality of different customers, wherein the establishing, dynamically configuring, and allocating the storage resources and processing resources are tailored to a first customer of the plurality of different customers, and wherein the method repeats the establishing, dynamically configuring, and allocating storage resources and processing resources tailored for each additional customer of the plurality of different customers.
A multi-tenant application system dynamically allocates storage and processing resources to individual customers within a shared infrastructure. The system addresses the challenge of efficiently managing resources in a multi-tenant environment where different customers have varying requirements. The application establishes a dedicated resource allocation framework for a first customer, dynamically configuring storage and processing resources based on that customer's specific needs. This process is repeated for each additional customer, ensuring that resource allocation is tailored to individual requirements while maintaining operational efficiency across the shared platform. The system optimizes resource utilization by dynamically adjusting allocations in response to changing demands, preventing resource contention and ensuring performance consistency for all customers. This approach enhances scalability and cost-effectiveness in multi-tenant cloud or enterprise applications by avoiding rigid, one-size-fits-all resource assignments. The solution is particularly useful in environments where customers have distinct workload patterns, security requirements, or performance expectations.
16. A computer system comprising: a memory; and a processor in communication with the memory, wherein the computer system is configured to perform a method, the method comprising: establishing an elastic network bandwidth allocation level that a network service provider of an elastic network is to provide to a data center for an application for transfer of data between the application and the elastic network, the application hosted at the data center, wherein the network service provider is configured to dynamically modify the elastic network bandwidth allocation level provided by the network service provider to the data center based on control by a component to change an amount of elastic network bandwidth being provided by the network service provider to the data center; dynamically configuring, for the application, elastic network bandwidth allocation to the data center from the network service provider in accordance with the established elastic network bandwidth allocation level; and allocating storage resources of the data center for the application and processing resources of the data center for the application, the allocating being based on the established elastic network bandwidth allocation level and providing storage resources and processing resources to operate at a level commensurate with the established elastic network bandwidth allocation level.
A computer system manages dynamic allocation of network bandwidth, storage, and processing resources in a data center hosting an application. The system addresses the challenge of efficiently scaling network and computational resources to match application demands in elastic network environments. The system establishes a baseline elastic network bandwidth allocation level for data transfer between the application and the network, provided by a network service provider. The provider can dynamically adjust this bandwidth based on control signals from a system component, allowing real-time scaling. The system then configures the allocated bandwidth for the application according to this level. Additionally, it allocates storage and processing resources in the data center proportionally to the established bandwidth level, ensuring all resources operate at a balanced capacity. This coordinated allocation prevents resource bottlenecks and optimizes performance by aligning network, storage, and compute resources with application needs. The dynamic adjustments enable efficient resource utilization and cost management in cloud or distributed computing environments.
17. The computer system of claim 16 , wherein the establishing comprises establishing the elastic network bandwidth allocation level based on anticipated network demand by the application.
A computer system dynamically adjusts network bandwidth allocation to optimize performance for applications running on virtual machines. The system monitors network traffic and application behavior to detect patterns that indicate future demand. Based on this analysis, it automatically adjusts the allocated bandwidth to ensure sufficient resources are available when needed, preventing congestion and latency issues. The system can scale bandwidth up or down in response to real-time conditions, such as increased user activity or data processing requirements. By anticipating network demand, the system ensures applications receive the necessary bandwidth to maintain performance without over-provisioning resources. This approach improves efficiency in cloud computing environments where multiple applications share network infrastructure. The system may also integrate with load balancing and traffic shaping mechanisms to further optimize network performance. The dynamic allocation process considers historical usage data, application priorities, and service-level agreements to determine appropriate bandwidth levels. This ensures critical applications receive priority access while non-critical tasks are allocated remaining resources. The system can operate across distributed networks, including hybrid cloud and multi-cloud environments, to provide consistent performance regardless of application location. By continuously adapting to changing network conditions, the system enhances reliability and user experience for cloud-based applications.
18. The computer system of claim 16 , wherein the storage resources comprise at least one selected from the group consisting of: storage input/output ports of a storage unit of the data center, and storage input/output operations per second of a storage unit of the data center.
This invention relates to a computer system for managing storage resources in a data center. The system monitors and optimizes storage performance by tracking specific storage metrics, including storage input/output (I/O) ports and I/O operations per second (IOPS) of storage units within the data center. These metrics are used to assess and allocate storage resources efficiently, ensuring optimal performance and resource utilization. The system dynamically adjusts storage configurations based on real-time data to prevent bottlenecks and improve overall data center efficiency. By focusing on key storage performance indicators, the system helps maintain high availability and reliability of storage resources, addressing challenges related to scalability and performance degradation in large-scale data center environments. The invention enhances storage management by providing granular control over storage I/O ports and IOPS, allowing for better load balancing and resource allocation. This approach ensures that storage resources are used effectively, reducing latency and improving response times for data-intensive applications. The system integrates with existing data center infrastructure to provide a comprehensive solution for storage resource optimization.
19. The computer system of claim 16 , wherein the processing resources comprise at least one selected from the group consisting of: virtualized storage area network processing power of a storage area network component or virtualized processor power for one or more application servers.
This invention relates to a computer system designed to optimize resource allocation in data centers or cloud computing environments. The system addresses the challenge of efficiently managing and distributing processing resources, particularly in virtualized environments where multiple applications and storage systems compete for computational power. The core innovation involves dynamically allocating processing resources based on demand, ensuring that critical workloads receive sufficient computational capacity while minimizing idle or underutilized resources. The system includes a resource allocation module that monitors the performance and demand of various components, such as storage area networks (SANs) and application servers. It dynamically adjusts the allocation of virtualized processing power to these components, either by reallocating SAN processing power or by redistributing virtualized CPU resources among application servers. This ensures that storage operations and application workloads are handled efficiently without bottlenecks. The system may also prioritize certain tasks or components based on predefined policies or real-time performance metrics, further optimizing resource utilization. By virtualizing and dynamically allocating processing power, the system improves scalability, reduces costs, and enhances overall system performance. This approach is particularly useful in environments where workloads fluctuate, such as cloud computing platforms or enterprise data centers. The invention ensures that resources are used optimally, preventing over-provisioning or underutilization of processing power.
20. The computer system of claim 16 , wherein the application comprises a multi-tenant application servicing a plurality of different customers, wherein the establishing, dynamically configuring, and allocating the storage resources and processing resources are tailored to a first customer of the plurality of different customers, and wherein the method repeats the establishing, dynamically configuring, and allocating storage resources and processing resources tailored for each additional customer of the plurality of different customers.
A computer system is designed to manage and allocate storage and processing resources for a multi-tenant application that serves multiple distinct customers. The system dynamically configures and allocates these resources based on the specific needs of each customer. For a first customer, the system establishes, configures, and allocates storage and processing resources tailored to that customer's requirements. This process is repeated for each additional customer, ensuring that the system adapts to the unique demands of every tenant. The dynamic allocation ensures efficient resource utilization while maintaining performance and security for each customer. This approach allows the multi-tenant application to scale and optimize resource allocation without compromising service quality for any individual customer. The system automates the configuration and allocation process, reducing manual intervention and improving operational efficiency. This solution addresses the challenge of managing shared resources in a multi-tenant environment while ensuring each customer receives customized and optimized performance.
Unknown
March 31, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.